Design of an AI Model for a Fully Automatic Grab-Type Ship Unloader System

Abstract

In seaports, the automatic Grab-Type Ship Unloader (GTSU) stands out for its ability to automatically load and unload materials, offering the potential for substantial productivity improvement and cost reduction. Developing a fully automatic GTSU, however, presents a unique challenge: the system must autonomously determine the position of the cargo hold and the coordinates of the working point and identify potential hazards during material loading and unloading. This paper proposes AI models designed to detect cargo holds, extract working points, and support collision risk warnings, utilizing both the LiDAR sensor and the camera in the GTSU system. The model for cargo hold detection and collision warning was developed using image data of the cargo hold and grab, employing the You Only Look Once model. Concurrently, the model responsible for extracting the coordinates of working points for the GTSU system was designed by integrating the cargo hold detection and point cloud processing models. After testing the AI models for the lab-scale GTSU, the results show that the cargo hold detection and collision warning models achieve an accuracy of approximately 96% and 90%, respectively. Additionally, the working point coordinates extracted from the sensor system show a deviation of 5–10% compared to traditional measurements.